© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 16876
    Prev
    Next
    INDEX
    Explanations

    mentions of salads

    oai_token-act-pair · gpt-3.5-turbo

    references to salad

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eff
    -0.75
    ITNESS
    -0.74
     Apostle
    -0.68
    FB
    -0.67
    drawn
    -0.66
    SPONSORED
    -0.64
    built
    -0.64
    abilities
    -0.63
    doing
    -0.63
    gone
    -0.63
    POSITIVE LOGITS
     salad
    1.16
     salads
    1.15
     Salad
    0.97
     greens
    0.97
    weed
    0.95
     dressing
    0.95
     tomatoes
    0.89
    bowl
    0.88
     lettuce
    0.86
     cabbage
    0.84
    Activations Density 0.007%

    No Known Activations